Changeset 34921 for main/trunk/greenstone2/perllib/cpan/Image/ExifTool/RSRC.pm

Timestamp:

2021-02-26T19:39:51+13:00 (3 years ago)

Author:

anupama

Message:

Committing the improvements to EmbeddedMetaPlugin's processing of Keywords vs other metadata fields. Keywords were literally stored as arrays of words rather than phrases in PDFs (at least in Diego's sample PDF), whereas other meta fields like Subjects and Creators stored them as arrays of phrases. To get both to work, Kathy updated EXIF to a newer version, to retrieve the actual EXIF values stored in the PDF. And Kathy and Dr Bainbridge came up with a new option that I added called apply_join_before_split_to_metafields that's a regex which can list the metadata fields to apply the join_before_split to and whcih previously always got applied to all metadata fields. Now it's applied to any *Keywords metafields by default, as that's the metafield we have experience of that behaves differently to the others, as it stores by word instead of phrases. Tested on Diego's sample PDF. Diego has double-checked it to works on his sample PDF too, setting the split char to ; and turning on the join_before_split and leaving apply_join_before_split_to_metafields at its default of .*Keywords. File changes are strings.properties for the tooltip, the plugin introducing the option and working with it and Kathy's EXIF updates affecting cpan/File and cpan/Image.

File:

• main/trunk/greenstone2/perllib/cpan/Image/ExifTool/RSRC.pm (modified) (10 diffs)

main/trunk/greenstone2/perllib/cpan/Image/ExifTool/RSRC.pm

@@ -15 +15 @@
 use Image::ExifTool qw(:DataAccess :Utils);
 
-$VERSION = '1.02';
+$VERSION = '1.09';
+
+sub ProcessRSRC($$);
 
 # Information decoded from Mac OS resources
 %Image::ExifTool::RSRC::Main = (
     GROUPS => { 2 => 'Document' },
+    PROCESS_PROC => \&ProcessRSRC,
     NOTES => q{
-        Tags extracted from Mac OS resource files and DFONT files.  These tags may
-        also be extracted from the resource fork of any file in OS X, either by
-        adding "/rsrc" to the filename to process the resource fork alone, or by
-        using the ExtractEmbedded (-ee) option to process the resource fork as a
-        sub-document of the main file.
+        Tags extracted from Mac OS resource files, DFONT files and "._" sidecar
+        files.  These tags may also be extracted from the resource fork of any file
+        in OS X, either by adding "/..namedfork/rsrc" to the filename to process the
+        resource fork alone, or by using the L<ExtractEmbedded|../ExifTool.html#ExtractEmbedded> (-ee) option to process
+        the resource fork as a sub-document of the main file.  When writing,
+        ExifTool preserves the Mac OS resource fork by default, but it may deleted
+        with C<-rsrc:all=> on the command line.
     },
     '8BIM' => {
@@ -34 +39 @@
         Name => 'Font',
         SubDirectory => { TagTable => 'Image::ExifTool::Font::Name' },
+    },
+    # my samples of postscript-type DFONT files have a POST resource
+    # with ID 0x1f5 and the same format as a PostScript file
+    'POST_0x01f5' => {
+        Name => 'PostscriptFont',
+        SubDirectory => { TagTable => 'Image::ExifTool::PostScript::Main' },
     },
     'usro_0x0000' => 'OpenWithApplication',
@@ -55 +66 @@
 sub ProcessRSRC($$)
 {
-    my ($exifTool, $dirInfo) = @_;
+    my ($et, $dirInfo) = @_;
     my $raf = $$dirInfo{RAF};
     my ($hdr, $map, $buff, $i, $j);
+
+    # allow access with data reference
+    $raf or $raf = new File::RandomAccess($$dirInfo{DataPt});
 
     # attempt to validate the format as thoroughly as practical
@@ -74 +88 @@
     my $typeOff = Get16u(\$map, 24);
     my $nameOff = Get16u(\$map, 26);
-    my $numTypes = Get16u(\$map, 28);
+    my $numTypes = (Get16u(\$map, 28) + 1) & 0xffff;
 
     # validate offsets in the resource map
     return 0 if $typeOff < 28 or $nameOff < 30;
 
-    $exifTool->SetFileType('RSRC') unless $$exifTool{IN_RESOURCE};
-    my $verbose = $exifTool->Options('Verbose');
+    $et->SetFileType('RSRC') unless $$et{IN_RESOURCE};
+    my $verbose = $et->Options('Verbose');
     my $tagTablePtr = GetTagTable('Image::ExifTool::RSRC::Main');
+    $et->VerboseDir('RSRC', $numTypes);
 
     # parse resource type list
-    for ($i=0; $i<=$numTypes; ++$i) {
+    for ($i=0; $i<$numTypes; ++$i) {
         my $off = $typeOff + 2 + 8 * $i;    # offset of entry in type list
         last if $off + 8 > $mapLen;
@@ -109 +124 @@
             if ($tagInfo or $verbose) {
                 unless ($raf->Seek($resOff, 0) and $raf->Read($buff, 4) == 4 and
-                        ($valLen = unpack('N', $buff)) < 1024000 and # arbitrary size limit
+                        ($valLen = unpack('N', $buff)) < 100000000 and # arbitrary size limit (100MB)
                         $raf->Read($val, $valLen) == $valLen)
                 {
-                    $exifTool->Warn("Error reading $resType resource");
+                    $et->Warn("Error reading $resType resource");
                     next;
                 }
@@ -120 +135 @@
                 $resName = '' unless $raf->Seek($resNameOff, 0) and $raf->Read($buff, 1) and
                     ($nameLen = ord $buff) != 0 and $raf->Read($resName, $nameLen) == $nameLen;
-                $exifTool->VPrint(0,sprintf("$resType resource ID 0x%.4x (offset 0x%.4x, $valLen bytes, name='$resName'):\n", $id, $resOff));
-                $exifTool->VerboseDump(\$val);
+                $et->VPrint(0,sprintf("%s resource ID 0x%.4x (offset 0x%.4x, $valLen bytes, name='%s'):\n",
+                    $resType, $id, $resOff, $resName));
+                $et->VerboseDump(\$val);
             }
             next unless $tagInfo;
@@ -133 +149 @@
                 next if $p + $vlen > $valLen;
                 my $tagTablePtr = GetTagTable('Image::ExifTool::RSRC::Main');
-                $val = $exifTool->Decode(substr($val, $p, $vlen), 'MacRoman');
+                $val = $et->Decode(substr($val, $p, $vlen), 'MacRoman');
             } elsif ($resType eq 'sfnt') {
                 # parse the OTF font block
@@ -139 +155 @@
                 $$dirInfo{Base} = $resOff + 4;
                 require Image::ExifTool::Font;
-                unless (Image::ExifTool::Font::ProcessOTF($exifTool, $dirInfo)) {
-                    $exifTool->Warn('Unrecognized sfnt resource format');
+                unless (Image::ExifTool::Font::ProcessOTF($et, $dirInfo)) {
+                    $et->Warn('Unrecognized sfnt resource format');
                 }
-                $exifTool->OverrideFileType('DFONT');
+                # assume this is a DFONT file unless processing the rsrc fork
+                $et->OverrideFileType('DFONT') unless $$et{DOC_NUM};
                 next;
             } elsif ($resType eq '8BIM') {
                 my $ttPtr = GetTagTable('Image::ExifTool::Photoshop::Main');
-                $exifTool->HandleTag($ttPtr, $id, $val,
+                $et->HandleTag($ttPtr, $id, $val,
                     DataPt  => \$val,
                     DataPos => $resOff + 4,
@@ -177 +194 @@
                 }
                 $val = \@vals;
+            } elsif ($resType eq 'POST') {
+                # assume this is a DFONT file unless processing the rsrc fork
+                $et->OverrideFileType('DFONT') unless $$et{DOC_NUM};
+                $val = substr $val, 2;
             } elsif ($resType ne 'TEXT') {
                 next;
             }
-            $exifTool->HandleTag($tagTablePtr, $tag, $val);
+            $et->HandleTag($tagTablePtr, $tag, $val);
         }
     }
@@ -205 +226 @@
 =head1 AUTHOR
 
-Copyright 2003-2011, Phil Harvey (phil at owl.phy.queensu.ca)
+Copyright 2003-2021, Phil Harvey (philharvey66 at gmail.com)
 
 This library is free software; you can redistribute it and/or modify it